Which surrogate insulin resistance indices best predict coronary artery disease? A machine learning approach
Authors' conclusion
Due to the simplicity of assessing the TyG-index with routine biochemical assays and given that the TyG-index was the most effective surrogate insulin resistance index for predicting CAD based on our results, it seems suitable for inclusion in future CAD prevention strategies.
Study context
- Population
- Individuals aged 20 to 74, followed for 9.9 years
- Participants
- 2,000 individuals
- Exposure
- Surrogate insulin resistance indices for predicting coronary artery disease (CAD)
- Outcome
- Occurrence of CAD
- Follow-up
- 9.9 years
Methodological detailsCox proportional hazard models, ROC analysis, machine learning feature selection (LASSO, Random Forest, Boruta)
- Cox proportional hazard models
- ROC analysis
- Machine learning feature selection (LASSO, Random Forest, Boruta)
Main finding
As reported in the abstract
| Group | HR (fully adjusted) | AUC |
|---|---|---|
| TyG-index | 2.54 (CI: 1.34-4.81) | 0.67 [0.63-0.7] |
TyG-index
HR (fully adjusted)2.54 (CI: 1.34-4.81)
AUC0.67 [0.63-0.7]
Observational data: associations, not effects.
Further findings
Association of TyG-index with CAD by sex
- The association was more prominent in females
Ceteris paribus profile of Random Forest
- Predictive ability of TyG-index increased steadily after 9 with a positive slope, without decline or leveling off
Original publication
Which surrogate insulin resistance indices best predict coronary artery disease? A machine learning approach. Cardiovasc Diabetol. Published 21 June 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →